Added experimental support for markdown

pre-commit.py

@@ -26,16 +26,145 @@ import datetime
 import subprocess
 import re
 import locale
+import markdown
+from hashlib import md5
 
 from functools import cmp_to_key
 from time import gmtime, strftime, mktime
 from bs4 import BeautifulSoup
 
 
+# ========================
+# Github Flavored Markdown
+# ========================
+
+def gfm(text):
+    # Extract pre blocks.
+    extractions = {}
+
+    def pre_extraction_callback(matchobj):
+        digest = md5(matchobj.group(0)).hexdigest()
+        extractions[digest] = matchobj.group(0)
+        return "{gfm-extraction-%s}" % digest
+    pattern = re.compile(r'<pre>.*?</pre>', re.MULTILINE | re.DOTALL)
+    text = re.sub(pattern, pre_extraction_callback, text)
+
+    # Prevent foo_bar_baz from ending up with an italic word in the middle.
+    def italic_callback(matchobj):
+        s = matchobj.group(0)
+        if list(s).count('_') >= 2:
+            return s.replace('_', '\_')
+        return s
+    text = re.sub(r'^(?! {4}|\t)\w+_\w+_\w[\w_]*', italic_callback, text)
+
+    # In very clear cases, let newlines become <br /> tags.
+    def newline_callback(matchobj):
+        if len(matchobj.group(1)) == 1:
+            return matchobj.group(0).rstrip() + ' \n'
+        else:
+            return matchobj.group(0)
+    pattern = re.compile(r'^[\w\<][^\n]*(\n+)', re.MULTILINE)
+    text = re.sub(pattern, newline_callback, text)
+
+    # Insert pre block extractions.
+    def pre_insert_callback(matchobj):
+        return '\n\n' + extractions[matchobj.group(1)]
+    text = re.sub(r'{gfm-extraction-([0-9a-f]{32})\}', pre_insert_callback,
+                  text)
+
+    return text
+
+
+# Test suite.
+try:
+    from nose.tools import assert_equal
+except ImportError:
+    def assert_equal(a, b):
+        assert a == b, '%r != %r' % (a, b)
+
+
+def test_single_underscores():
+    """Don't touch single underscores inside words."""
+    assert_equal(
+        gfm('foo_bar'),
+        'foo_bar',
+    )
+
+
+def test_underscores_code_blocks():
+    """Don't touch underscores in code blocks."""
+    assert_equal(
+        gfm(' foo_bar_baz'),
+        ' foo_bar_baz',
+    )
+
+
+def test_underscores_pre_blocks():
+    """Don't touch underscores in pre blocks."""
+    assert_equal(
+        gfm('<pre>\nfoo_bar_baz\n</pre>'),
+        '\n\n<pre>\nfoo_bar_baz\n</pre>',
+    )
+
+
+def test_pre_block_pre_text():
+    """Don't treat pre blocks with pre-text differently."""
+    a = '\n\n<pre>\nthis is `a\\_test` and this\\_too\n</pre>'
+    b = 'hmm<pre>\nthis is `a\\_test` and this\\_too\n</pre>'
+    assert_equal(
+        gfm(a)[2:],
+        gfm(b)[3:],
+    )
+
+
+def test_two_underscores():
+    """Escape two or more underscores inside words."""
+    assert_equal(
+        gfm('foo_bar_baz'),
+        'foo\\_bar\\_baz',
+    )
+
+
+def test_newlines_simple():
+    """Turn newlines into br tags in simple cases."""
+    assert_equal(
+        gfm('foo\nbar'),
+        'foo \nbar',
+    )
+
+
+def test_newlines_group():
+    """Convert newlines in all groups."""
+    assert_equal(
+        gfm('apple\npear\norange\n\nruby\npython\nerlang'),
+        'apple \npear \norange\n\nruby \npython \nerlang',
+    )
+
+
+def test_newlines_long_group():
+    """Convert newlines in even long groups."""
+    assert_equal(
+        gfm('apple\npear\norange\nbanana\n\nruby\npython\nerlang'),
+        'apple \npear \norange \nbanana\n\nruby \npython \nerlang',
+    )
+
+
+def test_newlines_list():
+    """Don't convert newlines in lists."""
+    assert_equal(
+        gfm('# foo\n# bar'),
+        '# foo\n# bar',
+    )
+    assert_equal(
+        gfm('* foo\n* bar'),
+        '* foo\n* bar',
+    )
+
 # =========
 # Functions
 # =========
 
+
 # Test if a variable exists (== isset function in PHP)
 # ====================================================
 def isset(variable):
@@ -110,7 +239,8 @@ def latest_articles(directory, number):
                  "from git.")
     latest_articles = latest_articles.strip().split("\n")
     latest_articles = [x for x in latest_articles if(isint(x[4:8]) and
-                                                     x.endswith(".html"))]
+                                                     (x.endswith(".html") or
+                                                      x.endswith(".md")))]
     latest_articles.sort(key=lambda x: (get_date(x)[4:8], get_date(x)[2:4],
                                         get_date(x)[:2], get_date(x)[9:]),
                          reverse=True)
@@ -289,7 +419,8 @@ for filename in list(added_files):
     except ValueError:
         pass
 
-    if ((not filename.endswith(".html") and not filename.endswith(".ignore"))
+    if ((not filename.endswith(".html") and not filename.endswith(".ignore")
+        and not filename.endswith(".md"))
        or direct_copy):
         # Note : this deal with CSS, images or footer file
         print("[INFO] (Direct copy) Copying directly the file "
@@ -327,7 +458,8 @@ for filename in list(modified_files):
     except ValueError:
         pass
 
-    if ((not filename.endswith("html") and not filename.endswith("ignore"))
+    if ((not filename.endswith(".html") and not filename.endswith(".ignore")
+        and not filename.endswith(".md"))
        or direct_copy):
         print("[INFO] (Direct copy) Updating directly the file "
               + filename[4:]+" in blog dir.")
@@ -336,7 +468,7 @@ for filename in list(modified_files):
         modified_files.remove(filename)
         continue
 
-    if filename.endswith("ignore"):
+    if filename.endswith(".ignore"):
         print("[INFO] (Not published) Found not published article "
               + filename[4:-7]+".")
         added_files.remove(filename)
@@ -364,7 +496,8 @@ for filename in list(deleted_files):
     except ValueError:
         pass
 
-    if ((not filename.endswith("html") and not filename.endswith("ignore"))
+    if ((not filename.endswith(".html") and not filename.endswith(".ignore")
+        and not filename.endswith(".md"))
        or (isset("direct_delete") and direct_delete is True)):
         print("[INFO] (Deleted file) Delete directly copied file "
               + filename[4:]+" in blog dir.")
@@ -560,6 +693,10 @@ for filename in added_files+modified_files:
         tags_comma += ("<a href=\""+params["BLOG_URL"] +
                        "/tags/"+tag+".html\">"+tag+"</a>")
 
+    # Markdown support
+    if filename.endswith(".md"):
+        article = markdown.markdown(gfm(article))
+
     # Write generated HTML for this article in gen /
     article = replace_tags(article, search_list, replace_list)